P. T.

Comparative Evaluation of a Custom CNN, Mobilenetv2, and A Lightweight Vision Transformer for Automated Woven-Fabric Weave-Pattern Classification

Weave-pattern identification is one of the more tedious quality-control steps in textile manufacturing, and most mills still rely on a trained inspector holding a swatch up to the light. This paper benchmarks three deep-learning classifiers — a custom convolutional neural network (CNN) built from scratch, a transfer-le...